Pai 的 AI 雷达
今天：Clean Engineering，GitHub Copilot weekly（Agent 原型）。并行还有 Click here to、Show HN、Terms of Service。
Language-model judges now gate training data, score generations, and drive leaderboards. The judge is then a measurement instrument, resting on one rarely stated assumption: the same request, sent to the same model name, reads the same tomorrow. We audited that assumption in two
Language-model judges now gate training data, score generations, and drive leaderboards. The judge is then a measurement instrument, resting on one rarely stated assumption: the same request, sent to the same model name, reads the same tomorrow. We audited that assumption in two
This week, GitHub Copilot expands model choice and content protections, while VS Code adds new ways to manage agent sessions and get pull requests merge-ready. GitHub Copilot, general Claude Fable 5.1 is available to Copilot Pro+, Max, Business, and Enterprise users. Gemini 3.8 F
OpenAI 通过 ChatGPT Work 和 Codex 向 Pro、Enterprise、Business Premium 计划用户开放 GPT-6 Astra，并通过 API、Microsoft Azure 和 AWS Bedrock 提供。 🔗 阅读原文 via AIHOT · https://aihot.virxact.com/items/cmto3ih1m016groxt2ypyqos3
I wanted to do something "new". I'm not 100% sure if this is really new since I don't really check out other people their portfolio's. It's been on my "to do" for a long time to redo my portfolio page. Now with AI coming and stuff, I thought I might as well do it like this. The o
Sam Altman 宣布 GPT-6 Astra 现已向所有 Plus 和 Business 用户推出。此前该模型已面向 Pro、Enterprise 和 Business Premium 用户在 Work/Codex 及 API 中提供。 🔗 阅读原文 via AIHOT · https://aihot.virxact.com/items/cmtnkdx8y031qroqs79optcp2
The emergence of agentic AI and LLM-based multi-agent systems (MAS) presents unprecedented opportunities for automating complex tasks, while simultaneously raising critical concerns about the preservation of fundamental human-centered values, such as privacy, fairness, and safety
Modern AI agent harnesses expose lifecycle hooks that bind shell commands to runtime events such as session start, tool calls, and file edits. These commands run with host privileges yet ship as lifecycle-hook configuration and may fire at times the LLM never observes. We identif
Retail supply chain operations rely on coupled decision modules that must adapt as requirements evolve. LLMs offer a natural-language interface for this task, but existing methods primarily focus on individual optimization models. Extending them to heterogeneous decision pipeline
Repository-level software engineering benchmarks have significantly advanced the evaluation of coding agents, but existing benchmarks primarily measure whether generated patches pass functional tests and overlook review-derived acceptance constraints (review constraints) that oft
Repository-level software engineering benchmarks have significantly advanced the evaluation of coding agents, but existing benchmarks primarily measure whether generated patches pass functional tests and overlook review-derived acceptance constraints (review constraints) that oft
AI agents are trained on population-scale data to encode broad capabilities spanning those of many practitioners. Yet the artifacts they produce rarely meet the personal bar professionals need to stake their reputation on. On realistic, open-ended tasks where success criteria are
AI agents are trained on population-scale data to encode broad capabilities spanning those of many practitioners. Yet the artifacts they produce rarely meet the personal bar professionals need to stake their reputation on. On realistic, open-ended tasks where success criteria are
AI agents are increasingly being developed and deployed across organizations using heterogeneous agent-development frameworks, AI models, tool interfaces, protocols, and execution environments. To realize their potential social and business impact, these agents must be able to in
AI agents are increasingly being developed and deployed across organizations using heterogeneous agent-development frameworks, AI models, tool interfaces, protocols, and execution environments. To realize their potential social and business impact, these agents must be able to in
AI agents have recently demonstrated strong performance in automated vulnerability patching. However, existing evaluations often validate a patch only by testing whether the provided Proof-of-Concept (PoC) input still triggers a crash. This leaves two key threats to validity: age